update

src/fastx_grep.nim

@@ -1,3 +1,12 @@
+# --------------------------------------------
+#                  LEGACY GREP 
+# --------------------------------------------
+
+#[
+   This is the original implementation made using
+   klib instead of readfq
+]#
+
 import klib
 import tables, strutils
 from os import fileExists

src/fastx_head.nim

@@ -1,4 +1,3 @@
-#import klib
 import readfq
 import strformat
 import tables, strutils

src/fastx_less.nim

@@ -0,0 +1,54 @@
+import readfq
+import strformat
+import tables, strutils
+from os import fileExists
+import docopt
+import ./seqfu_utils
+
+
+
+proc fastx_head_v2(argv: var seq[string]): int =
+    let args = docopt("""
+Usage: less [options] <file_1> [<file_2>]
+
+View a single FASTQ file or paired-end FASTQ dataset.
+
+Options:
+  -i, --interleaved      Input is interleaved paired-end FASTQ
+  -n, --num NUM          Print the first NUM sequences [default: 10]
+  -k, --skip SKIP        Print one sequence every SKIP [default: 0]
+  -p, --prefix STRING    Rename sequences with prefix + incremental number
+  -s, --strip-comments   Remove comments
+  -b, --basename         prepend basename to sequence name
+  -v, --verbose          Verbose output
+  --print-last           Print the name of the last sequence to STDERR (Last:NAME)
+  --fatal                Exit with error if less than NUM sequences are found
+  --quiet                Don't print warnings
+  --help                 Show this help
+
+
+  
+  """, version=version(), argv=argv)
+
+    var
+      num, skip    : int
+      prefix       : string
+      files        : seq[string]  
+      printBasename: bool 
+      separator    :  string 
+
+    let 
+      printLast     = bool(args["--print-last"])
+      fatalWarning  = bool(args["--fatal"])
+
+
+    if args["<file_1>"].len() == 0:
+      if getEnv("SEQFU_QUIET") == "":
+        stderr.writeLine("[seqfu head] Waiting for STDIN... [Ctrl-C to quit, type with --help for info].")
+      files.add("-")
+    else:
+      for file in args["<inputfile>"]:
+        files.add(file)
+
+
+

src/fastx_rc.nim

@@ -1,6 +1,5 @@
-import klib
-import strformat
-import tables, strutils
+import readfq
+import tables
 from os import fileExists
 import docopt
 import ./seqfu_utils
@@ -58,26 +57,21 @@ Options:
       else:
         echoVerbose(filename, verbose)
 
-      var 
-        f = xopen[GzFile](filename)
-        r: FastxRecord
-
-      defer: f.close()
-
-
-      while f.readFastx(r):
+      for record in readfq(filename):
+        var
+          r = record
         let comment = if len(r.comment) > 0 and not args["--strip-comments"]: " " & r.comment
                       else: ""
         if args["--only-rev"]:
-          r.seq = reverse(r.seq)
+          r.sequence = reverse(r.sequence)
         else:
-          r.seq = revcompl(r.seq)
+          r.sequence = revcompl(r.sequence)
 
-        if len(r.qual) > 0:
-          r.qual = reverse(r.qual)
-          echo '@', r.name, comment, "\n", r.seq, "\n+\n", r.qual
+        if len(r.quality) > 0:
+          r.quality = reverse(r.quality)
+          echo '@', r.name, comment, "\n", r.sequence, "\n+\n", r.quality
         else:
-          echo '>', r.name, comment, "\n", r.seq
+          echo '>', r.name, comment, "\n", r.sequence
 
 
 #[
@@ -138,12 +132,12 @@ Options:
         let comment = if len(r.comment) > 0 and not args["--strip-comments"]: " " & r.comment
                       else: ""
         if args["--only-rev"]:
-          outRecord.sequence = reverse(r.sequence)
+          outRecord.sequence = reverse(r.sequenceuence)
         else:
-          outRecord.sequence = revcompl(r.sequence)
+          outRecord.sequence = revcompl(r.sequenceuence)
 
-        if len(r.quality) > 0:
-          outRecord.quality = reverse(r.quality)
+        if len(r.qualityity) > 0:
+          outRecord.quality = reverse(r.qualityity)
           echo '@', outRecord.name, comment, "\n", outRecord.sequence, "\n+\n", outRecord.quality
         else:
           echo '>', outRecord.name, comment, "\n", outRecord.sequence

src/fastx_view.nim

@@ -1,4 +1,4 @@
-import klib
+import readfq
 import tables, strutils
 from os import fileExists
 import docopt
@@ -247,36 +247,32 @@ Options:
     stderr.writeLine("Error: input file not found: ", $args["<inputfile>"])
     quit(1)
 
-  var 
-    f = xopen[GzFile]($args["<inputfile>"])
-    read: FastxRecord
-
-  defer: f.close()
-  while f.readFastx(read):
+
+  for read in readfq($args["<inputfile>"]):
     # Print seq name
     if args["--nocolor"]:
       echo "@", read.name, "\t", read.comment
     else:
       echo "@", (read.name).bold, "\t", (read.comment).fgLightGray
 
     if $args["--oligo1"] != "nil":
-      let matches = findPrimerMatches(read.seq, $args["--oligo1"], matchThs, maxMismatches, minMatches)
-      let forString = highlightOligoMatches(read.seq, matches, len($args["--oligo1"]), bgBlue)
+      let matches = findPrimerMatches(read.sequence, $args["--oligo1"], matchThs, maxMismatches, minMatches)
+      let forString = highlightOligoMatches(read.sequence, matches, len($args["--oligo1"]), bgBlue)
       if forString.isOnlySpaces == false:
         echo forString
     if $args["--oligo2"] != "nil":
-      let matches = findPrimerMatches(read.seq, $args["--oligo2"], matchThs, maxMismatches, minMatches)
-      let revString = highlightOligoMatches(read.seq, matches, len($args["--oligo2"]), bgRed)
+      let matches = findPrimerMatches(read.sequence, $args["--oligo2"], matchThs, maxMismatches, minMatches)
+      let revString = highlightOligoMatches(read.sequence, matches, len($args["--oligo2"]), bgRed)
       if revString.isOnlySpaces == false:
         echo revString
-    echo read.seq
+    echo read.sequence
     if args["--qual-chars"]:
-      echo qualToColor(read.qual, thresholdValues, colorOutput)
+      echo qualToColor(read.quality, thresholdValues, colorOutput)
     else:
       if args["--ascii"]:
-        echo qualToAscii(read.qual, thresholdValues, colorOutput)
+        echo qualToAscii(read.quality, thresholdValues, colorOutput)
       else:
-        echo qualToUnicode(read.qual, thresholdValues, colorOutput)
+        echo qualToUnicode(read.quality, thresholdValues, colorOutput)
 
   if args["--verbose"]:
     stderr.writeLine("Encoding: ", ce)     

src/fqpair.nim

@@ -0,0 +1,47 @@
+import iterutils
+import sequtils
+import readfq
+import docopt
+import seqfu_utils
+
+template initClosure(id:untyped,iter:untyped) =
+  let id = iterator():auto {.closure.} =
+    for x in iter:
+      yield x
+
+iterator letters: auto =
+  for c in 'a' .. 'z':
+    yield c
+
+
+proc main(argv: var seq[string]): int =
+  let args =  docopt("""
+  USAGE:
+    fqpair FILE1 FILE2
+  """, argv=argv)
+
+  let
+    file1 = $args["FILE1"]
+    file2 = $args["FILE2"]
+
+  echo "Reading file1: ", file1
+  echo "Reading file2: ", file2
+
+  initClosure(f1,readfq(file1))
+  initClosure(f2,readfq(file2))
+
+  var
+    c = 0
+  for (fwd, rev) in zip(f1, f2):
+    var
+        newseq : FQRecord
+
+    newseq = fwd
+    newseq.sequence &= "*"
+    c = c + 1
+    echo c, "\tfwd: ", fwd.name, " : ", rev.name
+    echo newseq.sequence
+
+
+when isMainModule:
+  main_helper(main)

src/fu_cov.nim

@@ -1,5 +1,5 @@
 import klib
- 
+import readfq
 import docopt
 import strutils
 import stats
@@ -140,9 +140,7 @@ proc main(args: var seq[string]): int =
         echo "FATAL ERROR: File ", filename, " not found."
         quit(1)
 
-      var f = xopen[GzFile](filename)
-      defer: f.close()
-      var r: FastxRecord
+
       if args["--verbose"]:
         stderr.writeLine "Reading ", filename
 
@@ -151,10 +149,10 @@ proc main(args: var seq[string]): int =
       #var match: array[1, string]
 
 
-      while f.readFastx(r):
+      for r in readfq(filename):
         c+=1
-        total_bases += len(r.seq)
-        lenStats.push(len(r.seq))
+        total_bases += len(r.sequence)
+        lenStats.push(len(r.sequence))
         var cov = getCovFromString(r.name & " " & r.comment)
 
         # Coverage check
@@ -168,20 +166,20 @@ proc main(args: var seq[string]): int =
             continue
 
         # Contig length filter
-        if optminlen > 0 and len(r.seq) < optminlen:
+        if optminlen > 0 and len(r.sequence) < optminlen:
           skip_short += 1
           continue
-        if optmaxlen > 0 and len(r.seq) > optmaxlen:
+        if optmaxlen > 0 and len(r.sequence) > optmaxlen:
           skip_long += 1
           continue
 
 
         pf += 1
-        bases_printed += len(r.seq)
+        bases_printed += len(r.sequence)
         if args["--sort"] == false:
-          echo ">", r.name, " ", r.comment, "\n", r.seq;
+          echo ">", r.name, " ", r.comment, "\n", r.sequence;
         else:
-          covTable.add((name: r.name, comment: r.comment, cov: cov, length: len(r.seq), sequence: r.seq))
+          covTable.add((name: r.name, comment: r.comment, cov: cov, length: len(r.sequence), sequence: r.sequence))
     let
       ratio = 100.0 * float(bases_printed) / float(total_bases)